cinob/dsh-plugin-custom-provider-enhancer
⚡ DeepSeek Harness 自定义模型增强插件:在配置第三方提供商时,自动从权威模型库补齐上下文大小、Token 上限、视觉多模态输入与思考强度档位。
Project Overview项目介绍
DSH Custom Provider Enhancer is a native out-of-the-box Cordis plugin built exclusively for DeepSeek Harness (DSH). It is designed specifically to work with custom OpenAI-compatible model providers including OneAPI, NewAPI, OpenRouter, vLLM, and Ollama. When users discover or save models through DSH’s web GUI, the plugin automatically queries a database of over 3000 models to populate critical runtime parameters for connected custom models. Installation is straightforward: users can add it to their DSH web profile with a single terminal command, and it automatically mounts and activates without extra manual configuration.
When users connect third-party custom gateways to DSH, the default model discovery endpoint only returns raw model IDs and omits key parameters that DSH needs to function correctly. Missing context window sizes lead to inaccurate token counting and accidental context overflows, missing multimodal flags disable image uploads in the chat interface, and missing reasoning levels hide the thinking intensity slider. This plugin fixes all these issues by intercepting model discovery and resolution requests to inject the correct parameters, and it only affects custom providers so native DeepSeek channels remain untouched. It is built for any DSH user who connects custom third-party model providers to their DSH instance.
The plugin is compatible with DSH versions from 0.1.0-rc.1 to current mainline, Cordis 3.x, and Node.js versions 20, 22, and 24 and above. It works across all major desktop operating systems including Linux, macOS, and Windows. It includes fault tolerance features like built-in core model definitions, local caching, timeout circuit-breaking, and fuzzy matching for dated model snapshots, so it works even if the remote metadata database is unreachable. It is released under the open-source MIT license, with no associated costs or closed-source restrictions for users or developers.
这是一个专为 DeepSeek Harness (DSH) 开发的原生开箱即用 Cordis 插件,面向自定义模型提供商(例如 OneAPI、NewAPI、OpenRouter、vLLM、Ollama 以及其他兼容 OpenAI 格式的 API 网关)使用。当用户在 DSH 网页端 GUI 发现或保存模型时,插件会自动查询包含 3000 多个模型的数据库,自动填充上下文窗口大小、最大输出令牌、多模态视觉支持、深度推理能力等关键参数。
本插件解决了用户将第三方自定义网关接入 DSH 时,默认模型发现端点仅返回原始模型 ID、缺失关键运行参数的问题。缺失参数会导致令牌压力计量不准确、上下文溢出、无法启用对话界面的图片上传功能、推理强度滑块不显示等诸多问题。安装后插件会自动拦截模型发现请求,填充正确参数,且仅作用于自定义第三方提供商,不会改动原生 DeepSeek 通道。
作为标准 DSH 配置包插件,它仅需一条命令即可完成安装卸载,支持 DSH 0.1.0-rc.1 及以上主线版本、Cordis 3.x 框架,要求 Node.js 版本为 20+,同时兼容 Linux、macOS、Windows 全平台。它支持零配置开箱即用,内置容错和离线回退机制,可自动将参数写入配置文件,整体采用 MIT 开源许可协议。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-plugin-custom-provider-enhancer(cinob/dsh-plugin-custom-provider-enhancer)
仓库:https://github.com/cinob/dsh-plugin-custom-provider-enhancer
本站详情页:https://www.yhbd.top/plugins/cinob-dsh-plugin-custom-provider-enhancer/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-08-25 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- Only 2 stars - very few users, little community feedback星标只有 2,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add github:cinob/dsh-plugin-custom-provider-enhancer
把 cinob/dsh-plugin-custom-provider-enhancer 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
DSH Custom Provider Enhancer
English | 简体中文
DSH Custom Provider Enhancer is an out-of-the-box DeepSeek Harness (DSH) / Cordis plugin designed for Custom Model Providers (e.g. OneAPI, NewAPI, OpenRouter, vLLM, Ollama, and OpenAI-compatible API gateways).
When discovering or saving models in the Web GUI, it automatically queries a 3000+ model database to populate Context Window (contextWindow), Max Output Tokens (maxTokens), Multimodal Vision (input: [text, image]), and Deep Thinking / Reasoning (reasoningEfforts).
📋 Table of Contents
- Overview
- Compatibility
- Key Features
- Install
- Configuration
- Quick Start
- Permissions & Data Security
- Troubleshooting & Rollback
- Development & Testing
- License
🎯 Overview
What problem does it solve?
When users connect custom third-party gateways (e.g. OneAPI, NewAPI, vLLM, Ollama) to DeepSeek Harness, the standard GET /models discovery endpoint only returns raw model IDs (such as gemini-3.7-flash, deepseek-v4-pro, or mimo-v2.5). It omits critical runtime parameters:
- ❌ Missing context limits causes inaccurate token pressure metering or context overflows.
- ❌ Missing multimodal flags (
input: ['text', 'image']) disables image uploads in the conversation interface. - ❌ Missing reasoning levels (
reasoningEfforts) hides the thinking intensity slider in chat.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
IcedWatermelonJuice/dsh-provider-veark
loyalchiiina/dsh-chat-image-lightbox
Alisa0808/vox-director
ysr666/dsh-vision-router
Mars-Sea/dsh-commandcode-provider
ZSeven-W/dsh-ios
volcengine/ark-cli